---
title: Methodology
url: https://stowly.dev/methodology
description: How provider pricing becomes a cost estimate.
docs_index: https://stowly.dev/llms.txt
version: v0.1
lastUpdated: 2026-09-17
---

> Fetch the complete documentation index at https://stowly.dev/llms.txt before exploring further.
# Methodology

How provider pricing becomes the number you see — no black boxes.

1. **Sources first** — every rate starts from the provider's own pricing page. Full list: https://stowly.dev/sources
2. **Polled, not pasted** — rates are re-fetched every few minutes. A provider price change flows through on its own.
3. **Per-million math** — input, output, 5-minute cache write, 1-hour cache write, and cached input each carry their own price. Monthly estimate = token allocation × rate × request volume.
4. **Cache-aware by default** — cached versus fresh tokens are priced separately, never averaged.
5. **Tokens estimated, prices exact** — prompts are tokenized in your browser (~4 chars/token); per-million prices come verbatim from the source.
6. **Verified means cited and fresh** — a rate counts when it links back to a live provider page and was re-checked inside the polling window.